Model: GELU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1053 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 4.1350. Min Range: -4.1350

Max Act: 4.1350. Min Act: -0.1700

Data Index: 434211 (C4 (Web Text))

Max Activating Token Index: 395

Text #1

Max Range: 4.1350. Min Range: -4.1350

Max Act: 4.0412. Min Act: -0.1700

Data Index: 1311970 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 4.1350. Min Range: -4.1350

Max Act: 4.0724. Min Act: -0.1700

Data Index: 528590 (C4 (Web Text))

Max Activating Token Index: 404

Text #3

Max Range: 4.1350. Min Range: -4.1350

Max Act: 4.0412. Min Act: -0.1700

Data Index: 1169436 (C4 (Web Text))

Max Activating Token Index: 361

Text #4

Max Range: 4.1350. Min Range: -4.1350

Max Act: 4.0412. Min Act: -0.1700

Data Index: 1036324 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 4.1350. Min Range: -4.1350

Max Act: 4.0412. Min Act: -0.1700

Data Index: 370678 (C4 (Web Text))

Max Activating Token Index: 964

Text #6

Max Range: 4.1350. Min Range: -4.1350

Max Act: 4.0412. Min Act: -0.1700

Data Index: 507336 (C4 (Web Text))

Max Activating Token Index: 379

Text #7

Max Range: 4.1350. Min Range: -4.1350

Max Act: 4.0099. Min Act: -0.1700

Data Index: 795388 (C4 (Web Text))

Max Activating Token Index: 986

Text #8

Max Range: 4.1350. Min Range: -4.1350

Max Act: 3.9474. Min Act: -0.1700

Data Index: 1227608 (C4 (Web Text))

Max Activating Token Index: 421

Text #9

Max Range: 4.1350. Min Range: -4.1350

Max Act: 3.9161. Min Act: -0.1700

Data Index: 539342 (C4 (Web Text))

Max Activating Token Index: 790

Text #10

Max Range: 4.1350. Min Range: -4.1350

Max Act: 3.9474. Min Act: -0.1700

Data Index: 321846 (C4 (Web Text))

Max Activating Token Index: 16

Text #11

Max Range: 4.1350. Min Range: -4.1350

Max Act: 3.9474. Min Act: -0.1700

Data Index: 45366 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 4.1350. Min Range: -4.1350

Max Act: 3.9474. Min Act: -0.1700

Data Index: 582341 (C4 (Web Text))

Max Activating Token Index: 632

Text #13

Max Range: 4.1350. Min Range: -4.1350

Max Act: 3.9474. Min Act: -0.1700

Data Index: 1169409 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 4.1350. Min Range: -4.1350

Max Act: 3.9474. Min Act: -0.1700

Data Index: 461941 (C4 (Web Text))

Max Activating Token Index: 362

Text #15

Max Range: 4.1350. Min Range: -4.1350

Max Act: 3.9474. Min Act: -0.1700

Data Index: 1221065 (C4 (Web Text))

Max Activating Token Index: 566

Text #16

Max Range: 4.1350. Min Range: -4.1350

Max Act: 3.8848. Min Act: -0.1700

Data Index: 673623 (C4 (Web Text))

Max Activating Token Index: 946

Text #17

Max Range: 4.1350. Min Range: -4.1350

Max Act: 3.9161. Min Act: -0.1700

Data Index: 446309 (C4 (Web Text))

Max Activating Token Index: 35

Text #18

Max Range: 4.1350. Min Range: -4.1350

Max Act: 3.9161. Min Act: -0.1700

Data Index: 552664 (C4 (Web Text))

Max Activating Token Index: 479

Text #19

Max Range: 4.1350. Min Range: -4.1350

Max Act: 3.9474. Min Act: -0.1700

Data Index: 785387 (C4 (Web Text))

Max Activating Token Index: 745